Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 200 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2264. Min Range: -6.2264
Max Act: 6.2264. Min Act: -0.1700
Data Index: 5571222 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2264. Min Range: -6.2264
Max Act: 6.1639. Min Act: -0.1700
Data Index: 1627463 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2264. Min Range: -6.2264
Max Act: 6.1014. Min Act: -0.1700
Data Index: 7038699 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2264. Min Range: -6.2264
Max Act: 6.1014. Min Act: -0.1696
Data Index: 4091283 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2264. Min Range: -6.2264
Max Act: 6.1014. Min Act: -0.1700
Data Index: 3944655 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2264. Min Range: -6.2264
Max Act: 6.0389. Min Act: -0.1700
Data Index: 6333705 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2264. Min Range: -6.2264
Max Act: 6.0389. Min Act: -0.1700
Data Index: 7328966 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2264. Min Range: -6.2264
Max Act: 6.0077. Min Act: -0.1700
Data Index: 2282262 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2264. Min Range: -6.2264
Max Act: 6.0389. Min Act: -0.1700
Data Index: 3443429 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2264. Min Range: -6.2264
Max Act: 6.0077. Min Act: -0.1700
Data Index: 1027846 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2264. Min Range: -6.2264
Max Act: 6.0077. Min Act: -0.1700
Data Index: 6949194 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2264. Min Range: -6.2264
Max Act: 6.0077. Min Act: -0.1700
Data Index: 453424 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2264. Min Range: -6.2264
Max Act: 5.9764. Min Act: -0.1700
Data Index: 5387822 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2264. Min Range: -6.2264
Max Act: 5.9764. Min Act: -0.1700
Data Index: 4439945 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2264. Min Range: -6.2264
Max Act: 5.9764. Min Act: -0.1700
Data Index: 3462216 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2264. Min Range: -6.2264
Max Act: 5.9764. Min Act: -0.1700
Data Index: 3368895 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2264. Min Range: -6.2264
Max Act: 5.9452. Min Act: -0.1700
Data Index: 1752739 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2264. Min Range: -6.2264
Max Act: 5.9452. Min Act: -0.1700
Data Index: 4168021 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2264. Min Range: -6.2264
Max Act: 5.9452. Min Act: -0.1700
Data Index: 4642631 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2264. Min Range: -6.2264
Max Act: 5.9452. Min Act: -0.1700
Data Index: 720099 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #19